Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f22a4eb3076419e64b3e86b5a0207a41797c1f96fba23a7c966be45e8360ade
+oid sha256:f64b9258ac80da142a63acc7cbf6876522c5103b777c1b955bc27f1408ca0516
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9df2739512a80a8743368ba93b033e954f6e679903f0825c40eed9fadfe8bd8
+oid sha256:a15194f0f584809f7f084c3d3c8e9527a461cca8df33091cb05007bf58d7c1a1
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e76b0bdd4a6c1a2caaba386eb7c5636c76a1737d9e3b0a5835e28101b0fa6f6
+oid sha256:dd3f07e2983188d4722a82fd116dd58664f39b493fc1be3b04e80cfa19f1df0b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f6076e5f87cfeed29d6697d7b3e8756e16f70e9a7340fdc15fd1d81e542f980
+oid sha256:f939f73d23e2dbcf206924457b3eb57b1e3cb5e54dc5c680d84d6737616b0365
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4283676147460938,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.015722034431255406,
+  "best_metric": 1.309641718864441,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.018342373503131306,
   "eval_steps": 50,
-  "global_step": 300,
+  "global_step": 350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,49 @@
       "eval_samples_per_second": 16.417,
       "eval_steps_per_second": 4.105,
       "step": 300
+    },
+    {
+      "epoch": 0.016246102245630584,
+      "grad_norm": 1.416838526725769,
+      "learning_rate": 7.73239666488339e-05,
+      "loss": 1.1683,
+      "step": 310
+    },
+    {
+      "epoch": 0.016770170060005765,
+      "grad_norm": 1.574950933456421,
+      "learning_rate": 7.048026657375537e-05,
+      "loss": 1.0502,
+      "step": 320
+    },
+    {
+      "epoch": 0.017294237874380947,
+      "grad_norm": 1.8394525051116943,
+      "learning_rate": 6.379012747157697e-05,
+      "loss": 1.0767,
+      "step": 330
+    },
+    {
+      "epoch": 0.017818305688756125,
+      "grad_norm": 2.86199688911438,
+      "learning_rate": 5.7286143027514095e-05,
+      "loss": 1.1481,
+      "step": 340
+    },
+    {
+      "epoch": 0.018342373503131306,
+      "grad_norm": 12.534944534301758,
+      "learning_rate": 5.100000000000002e-05,
+      "loss": 1.8794,
+      "step": 350
+    },
+    {
+      "epoch": 0.018342373503131306,
+      "eval_loss": 1.309641718864441,
+      "eval_runtime": 490.402,
+      "eval_samples_per_second": 16.385,
+      "eval_steps_per_second": 4.097,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.65692592029696e+16,
+  "total_flos": 6.59974690701312e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null